Inspiration

We’ve all opened a dataset and thought, “What the hell am I looking at?” so i built something that explains it for you- fast.

What it does

You upload a CSV, it gives you an AI-generated summary, and you can search those insights later using natural language. It tells you the type of data, highlights quality issues, and suggests cleaning steps and visualizations including which charts or plots would be most useful for different columns

How we built it

React frontend, FastAPI backend, used Gemini for analysis(no gcp credits unfortunately🥲), MongoDB Atlas for storing vectors, and a clean vector search setup.

Challenges we ran into

Getting vector search to play nice with MongoDB was trickier than expected but overall was fun building it.

Accomplishments that we're proud of

The AI summaries are actually useful, the search works like magic and it’s all stitched together in a simple UI

What we learned

Fast iteration with AI and databases takes finesse- but when it clicks, it really clicks

What's next for NarratAIve Data Analyzer

Multi-file uploads, visualizations for each dataset, smarter trend detection, and turning it into a full-blown AI-powered data assistant not just a smart notetaker

Built With

Share this project:

Updates